joepie91
/
resolv
1
0
Fork 0
Code Issues Pull Requests Releases Wiki Activity

Update the shared code and all resolvers for the new class-based model

Browse Source
master
Sven Slootweg 12 years ago
parent 92bceed168
commit 88e6819bf2
10 changed files with 461 additions and 341 deletions
Show Stats Download Patch File Download Diff File

29
resolv/__init__.py
Unescape Escape View File

@ -1,21 +1,28 @@
import re import re
from resolvers import * import resolvers
def resolve(url): def resolve(url):
if re.match("https?:\/\/(www\.)?putlocker\.com", url) is not None: if re.match("https?:\/\/(www\.)?putlocker\.com", url) is not None:
return putlocker.resolve(url) task = resolvers.PutlockerTask(url)
return task.run()
elif re.match("https?:\/\/(www\.)?sockshare\.com", url) is not None: elif re.match("https?:\/\/(www\.)?sockshare\.com", url) is not None:
return sockshare.resolve(url) task = resolvers.SockshareTask(url)
return task.run()
elif re.match("https?:\/\/(www\.)?1channel\.ch\/external\.php", url) is not None: elif re.match("https?:\/\/(www\.)?1channel\.ch\/external\.php", url) is not None:
return onechannel.resolve(url) task = resolvers.OneChannelTask(url)
return task.run()
elif re.match("https?:\/\/(www\.)?youtube\.com\/watch\?", url) is not None: elif re.match("https?:\/\/(www\.)?youtube\.com\/watch\?", url) is not None:
return youtube.resolve(url) task = resolvers.YoutubeTask(url)
return task.run()
elif re.match("https?:\/\/(www\.)?filebox\.com\/[a-zA-Z0-9]+", url) is not None: elif re.match("https?:\/\/(www\.)?filebox\.com\/[a-zA-Z0-9]+", url) is not None:
return filebox.resolve(url) task = resolvers.FileboxTask(url)
return task.run()
elif re.match("https?:\/\/(www\.)?pastebin\.com\/[a-zA-Z0-9]+", url) is not None: elif re.match("https?:\/\/(www\.)?pastebin\.com\/[a-zA-Z0-9]+", url) is not None:
return pastebin.resolve(url) task = resolvers.PastebinTask(url)
return task.run()
elif re.match("https?:\/\/(www\.)?mediafire\.com\/\?[a-z0-9]+", url) is not None: elif re.match("https?:\/\/(www\.)?mediafire\.com\/\?[a-z0-9]+", url) is not None:
return mediafire.resolve(url) task = resolvers.MediafireTask(url)
return task.run()
else: else:
return {} return {}
@ -25,10 +32,10 @@ def recurse(url):
while True: while True:
result = resolve(url) result = resolve(url)
if result == {}: if result.state != "finished":
return previous_result return previous_result
elif 'url' not in result: elif result.result_type != "url":
return result return result
url = result['url'] url = result.results['url']
previous_result = result previous_result = result

11
resolv/resolvers/dummy.py
Unescape Escape View File

@ -1,2 +1,9 @@
def resolve(input): from resolv.shared import Task
return {'dummy': input}
class DummyTask(Task):
result_type = "dummy"
def run(self):
self.results = {'dummy': self.url}
self.state = "finished"
return self

89
resolv/resolvers/filebox.py
Unescape Escape View File

@ -1,70 +1,43 @@
import re, time, urllib2 import re, time, urllib2
from resolv.shared import ResolverError from resolv.shared import ResolverError, Task
def resolve(url): class FileboxTask(Task):
matches = re.search("https?:\/\/(www\.)?filebox\.com\/([a-zA-Z0-9]+)", url) result_type = "video"
if matches is None: def run(self):
raise ResolverError("The provided URL is not a valid Filebox.com URL.") matches = re.search("https?:\/\/(www\.)?filebox\.com\/([a-zA-Z0-9]+)", self.url)
video_id = matches.group(2) if matches is None:
self.state = "invalid"
raise ResolverError("The provided URL is not a valid Filebox.com URL.")
try: video_id = matches.group(2)
contents = urllib2.urlopen("http://www.filebox.com/embed-%s-970x543.html" % video_id).read()
except:
raise ResolverError("Could not retrieve the video page.")
matches = re.search("url: '([^']+)',", contents) try:
contents = self.fetch_page("http://www.filebox.com/embed-%s-970x543.html" % video_id)
except urllib2.URLError, e:
self.state = "failed"
raise ResolverError("Could not retrieve the video page.")
if matches is None: matches = re.search("url: '([^']+)',", contents)
raise ResolverError("No video was found on the specified URL.")
video_file = matches.group(1) if matches is None:
self.state = "invalid"
raise ResolverError("No video was found on the specified URL. The Filebox.com resolver currently only supports videos.")
stream_dict = { video_file = matches.group(1)
'url' : video_file,
'quality' : "unknown",
'priority' : 1,
'format' : "unknown"
}
return { 'title': "", 'videos': [stream_dict] } stream_dict = {
'url' : video_file,
'quality' : "unknown",
'priority' : 1,
'format' : "unknown"
}
def resolve2(url): self.results = {
# This is a fallback function in case no video could be found through the resolve() method. 'title': "",
# It's not recommended to use it, as it introduces a 5 second wait. 'videos': [stream_dict]
}
try: self.state = "finished"
import mechanize return self
except ImportError:
raise ResolverError("The Python mechanize module is required to resolve Filebox.com URLs.")
matches = re.search("https?:\/\/(www\.)?filebox\.com\/([a-zA-Z0-9]+)", url)
if matches is None:
raise ResolverError("The provided URL is not a valid Filebox.com URL.")
try:
browser = mechanize.Browser()
browser.set_handle_robots(False)
browser.open(url)
except:
raise ResolverError("The Filebox.com site could not be reached.")
time.sleep(6)
try:
browser.select_form(nr=0)
result = browser.submit()
page = result.read()
except Exception, e:
raise ResolverError("The file was removed, or the URL is incorrect.")
matches = re.search("this\.play\('([^']+)'\)", page)
if matches is None:
raise ResolverError("No video file was found on the given URL; the Filebox.com server for this file may be in maintenance mode, or the given URL may not be a video file. The Filebox.com resolver currently only supports video links.")
video_file = matches.group(1)
return { 'title': "", 'videos': { 'video': video_file } }

52
resolv/resolvers/mediafire.py
Unescape Escape View File

@ -1,28 +1,40 @@
import re, urllib2 import re, urllib2
from resolv.shared import ResolverError, unescape from resolv.shared import ResolverError, unescape, Task
def resolve(url): class MediafireTask(Task):
try: result_type = "file"
contents = urllib2.urlopen(url).read()
except:
raise ResolverError("Could not retrieve the specified URL.")
matches = re.search('kNO = "([^"]+)";', contents) def run(self):
try:
contents = self.fetch_page(self.url)
except urllib2.URLError, e:
self.state = "failed"
raise ResolverError("Could not retrieve the specified URL.")
if matches is None: matches = re.search('kNO = "([^"]+)";', contents)
raise ResolverError("No download was found on the given URL; the server for this file may be in maintenance mode, or the given URL may not be valid. It is also possible that you have been blocked - CAPTCHA support is not yet present.")
file_url = matches.group(1) if matches is None:
self.state = "failed"
raise ResolverError("No download was found on the given URL; the server for this file may be in maintenance mode, or the given URL may not be valid. It is also possible that you have been blocked - CAPTCHA support is not yet present.")
try: file_url = matches.group(1)
file_title = unescape(re.search('<title>([^<]+)<\/title>', contents).group(1))
except:
raise ResolverError("Could not find the download title.")
file_dict = { try:
'url' : file_url, file_title = unescape(re.search('<title>([^<]+)<\/title>', contents).group(1))
'priority' : 1, except:
'format' : "unknown" self.state = "failed"
} raise ResolverError("Could not find the download title.")
return { 'title': file_title, 'files': [file_dict] } file_dict = {
'url' : file_url,
'priority' : 1,
'format' : "unknown"
}
self.results = {
'title': file_title,
'files': [file_dict]
}
self.state = "finished"
return self

27
resolv/resolvers/onechannel.py
Unescape Escape View File

@ -1,15 +1,22 @@
import re, base64 import re, base64
from resolv.shared import ResolverError from resolv.shared import ResolverError, Task
def resolve(url): class OneChannelTask(Task):
matches = re.search("https?:\/\/(www\.)?1channel\.ch\/external\.php\?.*url=([^&]+)", url) result_type = "url"
if matches is None: def run(self):
raise ResolverError("The provided URL is not a valid external 1channel URL.") matches = re.search("https?:\/\/(www\.)?1channel\.ch\/external\.php\?.*url=([^&]+)", self.url)
try: if matches is None:
real_url = base64.b64decode(matches.group(2)).strip() self.state = "invalid"
except TypeError: raise ResolverError("The provided URL is not a valid external 1channel URL.")
raise ResolverError("The provided URL is malformed.")
return { 'url': real_url } try:
real_url = base64.b64decode(matches.group(2)).strip()
except TypeError:
self.state = "failed"
raise ResolverError("The provided URL is malformed.")
self.results = { 'url': real_url }
self.state = "finished"
return self

54
resolv/resolvers/pastebin.py
Unescape Escape View File

@ -1,30 +1,42 @@
import re, urllib, urllib2 import re, urllib2
from resolv.shared import ResolverError, unescape from resolv.shared import ResolverError, unescape, Task
def resolve(url): class PastebinTask(Task):
matches = re.search("https?:\/\/(www\.)?pastebin\.com\/([a-zA-Z0-9]+)", url) result_type = "text"
if matches is None: def run(self):
raise ResolverError("The provided URL is not a valid Pastebin URL.") matches = re.search("https?:\/\/(www\.)?pastebin\.com\/([a-zA-Z0-9]+)", self.url)
paste_id = matches.group(2) if matches is None:
self.state = "invalid"
raise ResolverError("The provided URL is not a valid Pastebin URL.")
try: paste_id = matches.group(2)
contents = urllib2.urlopen(url).read()
except:
raise ResolverError("Could not retrieve the specified URL. The specified paste may not exist.")
matches = re.search("<h1>([^<]+)</h1>", contents) try:
contents = self.fetch_page(self.url)
except urllib2.URLError, e:
self.state = "failed"
raise ResolverError("Could not retrieve the specified URL. The paste may not exist.")
if matches is None: matches = re.search("<h1>([^<]+)</h1>", contents)
raise ResolverError("The provided URL is not a valid paste.")
paste_title = unescape(matches.group(1)) if matches is None:
self.state = "invalid"
raise ResolverError("The provided URL is not a valid paste.")
file_dict = { paste_title = unescape(matches.group(1))
'url' : "http://pastebin.com/download.php?i=%s" % paste_id,
'priority' : 1,
'format' : "text"
}
return { 'title': paste_title, 'files': [file_dict] } resolved = {
'url' : "http://pastebin.com/download.php?i=%s" % paste_id,
'priority' : 1,
'format' : "text"
}
self.results = {
'title': paste_title,
'files': [resolved]
}
self.state = "finished"
return self

138
resolv/resolvers/putlocker.py
Unescape Escape View File

@ -1,62 +1,78 @@
import re import re
from resolv.shared import ResolverError, unescape from resolv.shared import ResolverError, unescape, Task
def resolve(url): class PutlockerTask(Task):
try: result_type = "video"
import mechanize
except ImportError: def run(self):
raise ResolverError("The Python mechanize module is required to resolve PutLocker URLs.") try:
import mechanize
matches = re.search("https?:\/\/(www\.)?putlocker\.com\/(file|embed)\/([A-Z0-9]+)", url) except ImportError:
self.state = "failed"
if matches is None: raise ResolverError("The Python mechanize module is required to resolve PutLocker URLs.")
raise ResolverError("The provided URL is not a valid PutLocker URL.")
matches = re.search("https?:\/\/(www\.)?putlocker\.com\/(file|embed)\/([A-Z0-9]+)", self.url)
video_id = matches.group(3)
if matches is None:
try: self.state = "invalid"
browser = mechanize.Browser() raise ResolverError("The provided URL is not a valid PutLocker URL.")
browser.set_handle_robots(False)
browser.open("http://putlocker.com/embed/%s" % video_id) video_id = matches.group(3)
except:
raise ResolverError("The PutLocker site could not be reached.") try:
browser = mechanize.Browser()
try: browser.set_handle_robots(False)
browser.select_form(nr=0) browser.open("http://putlocker.com/embed/%s" % video_id)
result = browser.submit() except:
page = result.read() self.state = "failed"
except Exception, e: raise ResolverError("The PutLocker site could not be reached.")
raise ResolverError("The file was removed, or the URL is incorrect.")
try:
matches = re.search("playlist: '([^']+)'", page) browser.select_form(nr=0)
result = browser.submit()
if matches is None: page = result.read()
raise ResolverError("No playlist was found on the given URL; the PutLocker server for this file may be in maintenance mode, or the given URL may not be a video file. The PutLocker resolver currently only supports video links.") except Exception, e:
self.state = "nonexistent"
playlist = matches.group(1) raise ResolverError("The file was removed, or the URL is incorrect.")
try: matches = re.search("playlist: '([^']+)'", page)
browser.open("http://www.putlocker.com%s" % playlist)
except: if matches is None:
raise ResolverError("The playlist file for the given URL could not be loaded.") raise ResolverError("No playlist was found on the given URL; the PutLocker server for this file may be in maintenance mode, or the given URL may not be a video file. The PutLocker resolver currently only supports video links.")
matches = re.search("url=\"([^\"]+)\" type=\"video\/x-flv\"", browser.response().read()) playlist = matches.group(1)
if matches is None: try:
raise ResolverError("The playlist file does not contain any video URLs. The PutLocker resolver currently only supports video links.") browser.open("http://www.putlocker.com%s" % playlist)
except:
video_file = matches.group(1) self.state = "failed"
raise ResolverError("The playlist file for the given URL could not be loaded.")
try:
video_title = unescape(re.search('<a href="\/file\/[^"]+"[^>]*><strong>([^<]*)<\/strong><\/a>', page).group(1)) matches = re.search("url=\"([^\"]+)\" type=\"video\/x-flv\"", browser.response().read())
except:
raise ResolverError("Could not find the video title.") if matches is None:
self.state = "failed"
stream_dict = { raise ResolverError("The playlist file does not contain any video URLs. The PutLocker resolver currently only supports video links.")
'url' : video_file,
'quality' : "unknown", video_file = matches.group(1)
'priority' : 1,
'format' : "unknown" try:
} video_title = unescape(re.search('<a href="\/file\/[^"]+"[^>]*><strong>([^<]*)<\/strong><\/a>', page).group(1))
except:
return { 'title': video_title, 'videos': [stream_dict] } self.state = "failed"
raise ResolverError("Could not find the video title.")
stream_dict = {
'url' : video_file,
'quality' : "unknown",
'priority' : 1,
'format' : "unknown"
}
self.results = {
'title': video_title,
'videos': [stream_dict]
}
self.state = "finished"
return self

138
resolv/resolvers/sockshare.py
Unescape Escape View File

@ -1,62 +1,78 @@
import re import re
from resolv.shared import ResolverError, unescape from resolv.shared import ResolverError, unescape, Task
def resolve(url): class SockshareTask(Task):
try: result_type = "video"
import mechanize
except ImportError: def run(self):
raise ResolverError("The Python mechanize module is required to resolve SockShare URLs.") try:
import mechanize
matches = re.search("https?:\/\/(www\.)?sockshare\.com\/(file|embed)\/([A-Z0-9]+)", url) except ImportError:
self.state = "failed"
if matches is None: raise ResolverError("The Python mechanize module is required to resolve Sockshare URLs.")
raise ResolverError("The provided URL is not a valid SockShare URL.")
matches = re.search("https?:\/\/(www\.)?sockshare\.com\/(file|embed)\/([A-Z0-9]+)", self.url)
video_id = matches.group(3)
if matches is None:
try: self.state = "invalid"
browser = mechanize.Browser() raise ResolverError("The provided URL is not a valid Sockshare URL.")
browser.set_handle_robots(False)
browser.open("http://sockshare.com/embed/%s" % video_id) video_id = matches.group(3)
except:
raise ResolverError("The SockShare site could not be reached.") try:
browser = mechanize.Browser()
try: browser.set_handle_robots(False)
browser.select_form(nr=0) browser.open("http://sockshare.com/embed/%s" % video_id)
result = browser.submit() except:
page = result.read() self.state = "failed"
except Exception, e: raise ResolverError("The Sockshare site could not be reached.")
raise ResolverError("The file was removed, or the URL is incorrect.")
try:
matches = re.search("playlist: '([^']+)'", page) browser.select_form(nr=0)
result = browser.submit()
if matches is None: page = result.read()
raise ResolverError("No playlist was found on the given URL; the SockShare server for this file may be in maintenance mode, or the given URL may not be a video file. The SockShare resolver currently only supports video links.") except Exception, e:
self.state = "nonexistent"
playlist = matches.group(1) raise ResolverError("The file was removed, or the URL is incorrect.")
try: matches = re.search("playlist: '([^']+)'", page)
browser.open("http://www.sockshare.com%s" % playlist)
except: if matches is None:
raise ResolverError("The playlist file for the given URL could not be loaded.") raise ResolverError("No playlist was found on the given URL; the Sockshare server for this file may be in maintenance mode, or the given URL may not be a video file. The Sockshare resolver currently only supports video links.")
matches = re.search("url=\"([^\"]+)\" type=\"video\/x-flv\"", browser.response().read()) playlist = matches.group(1)
if matches is None: try:
raise ResolverError("The playlist file does not contain any video URLs. The SockShare resolver currently only supports video links.") browser.open("http://www.sockshare.com%s" % playlist)
except:
video_file = matches.group(1) self.state = "failed"
raise ResolverError("The playlist file for the given URL could not be loaded.")
try:
video_title = unescape(re.search('<a href="\/file\/[^"]+"[^>]*><strong>([^<]*)<\/strong><\/a>', page).group(1)) matches = re.search("url=\"([^\"]+)\" type=\"video\/x-flv\"", browser.response().read())
except:
raise ResolverError("Could not find the video title.") if matches is None:
self.state = "failed"
stream_dict = { raise ResolverError("The playlist file does not contain any video URLs. The Sockshare resolver currently only supports video links.")
'url' : video_file,
'quality' : "unknown", video_file = matches.group(1)
'priority' : 1,
'format' : "unknown" try:
} video_title = unescape(re.search('<a href="\/file\/[^"]+"[^>]*><strong>([^<]*)<\/strong><\/a>', page).group(1))
except:
return { 'title': video_title, 'videos': [stream_dict] } self.state = "failed"
raise ResolverError("Could not find the video title.")
stream_dict = {
'url' : video_file,
'quality' : "unknown",
'priority' : 1,
'format' : "unknown"
}
self.results = {
'title': video_title,
'videos': [stream_dict]
}
self.state = "finished"
return self

199
resolv/resolvers/youtube.py
Unescape Escape View File

@ -1,88 +1,117 @@
import re, urllib, urllib2 import re, urllib, urllib2, urlparse
from resolv.shared import ResolverError, unescape from resolv.shared import ResolverError, unescape, Task
def resolve(url): class YoutubeTask(Task):
try: result_type = "video"
contents = urllib2.urlopen(url).read()
except: extra_headers = {
raise ResolverError("Could not retrieve the specified URL.") 'Accept-Charset': 'ISO-8859-1,utf-8;q=0.7,*;q=0.7',
'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8',
map_start = "url_encoded_fmt_stream_map=" 'Accept-Language': 'en-us,en;q=0.5'
map_end = "\\u0026amp;" }
try: def run(self):
pos_start = contents.index(map_start) + len(map_start) + 6 try:
snippet = contents[pos_start:] contents = self.fetch_page(self.url)
except ValueError: except urllib2.URLError, e:
raise ResolverError("The starting position for the YouTube player configuration could not be found. Is the URL really a valid video page?") self.state = "failed"
raise ResolverError("Could not retrieve the specified URL.")
try:
pos_end = snippet.index(map_end) map_start = "url_encoded_fmt_stream_map="
stream_map = snippet[:pos_end] map_end = "\\u0026amp;"
except ValueError:
raise ResolverError("The ending position for the YouTube player configuration could not be found.") try:
pos_start = contents.index(map_start) + len(map_start)
try: snippet = contents[pos_start:]
stream_map = urllib.unquote(stream_map) except ValueError:
streams = stream_map.split(',url=') self.state = "failed"
except: raise ResolverError("The starting position for the YouTube player configuration could not be found. Is the URL really a valid video page?")
raise ResolverError("The YouTube player configuration is corrupted.")
try:
stream_pool = [] pos_end = snippet.index(map_end)
stream_map = snippet[:pos_end]
for stream in streams: except ValueError:
fields = stream.split('&') self.state = "failed"
raise ResolverError("The ending position for the YouTube player configuration could not be found.")
if len(fields) < 5:
raise ResolverError("The amount of fields in the YouTube player configuration is incorrect.") try:
stream_map = urllib.unquote(stream_map)
video_url = urllib.unquote(fields[0]) streams = stream_map.split(',')
quality = fields[1].split("=")[1] except:
fallback_host = fields[2].split("=")[1] self.state = "failed"
mimetype = urllib.unquote(fields[3].split("=")[1]) raise ResolverError("The YouTube player configuration is corrupted.")
itag = fields[4].split("=", 2)[1]
stream_pool = []
if mimetype.startswith("video/mp4"):
video_format = "mp4"
elif mimetype.startswith("video/x-flv"):
video_format = "flv"
elif mimetype.startswith("video/3gpp"):
video_format = "3gp"
elif mimetype.startswith("video/webm"):
video_format = "webm"
else:
video_format = "unknown"
if quality == "small":
video_quality = "240p"
video_priority = 5
elif quality == "medium":
video_quality = "360p"
video_priority = 4
elif quality == "large":
video_quality = "480p"
video_priority = 3
elif quality == "hd720":
video_quality = "720p"
video_priority = 2
elif quality == "hd1080":
video_quality = "1080p"
video_priority = 1
else:
video_quality = "unknown"
stream_dict = {
'url' : video_url,
'quality' : video_quality,
'priority' : video_priority,
'format' : video_format
}
stream_pool.append(stream_dict) for stream in streams:
fields = urlparse.parse_qs(stream)
try: if len(fields) < 6:
video_title = unescape(re.search('<meta property="og:title" content="([^"]*)">', contents).group(1)) self.state = "failed"
except: raise ResolverError("The amount of fields in the YouTube player configuration is incorrect.")
raise ResolverError("Could not find the video title.")
signature = fields['sig'][0]
video_url = "%s&signature=%s" % (fields['url'][0], signature)
quality = fields['quality'][0]
fallback_host = fields['fallback_host'][0]
mimetype = fields['type'][0]
itag = fields['itag'][0]
if mimetype.startswith("video/mp4"):
video_format = "mp4"
elif mimetype.startswith("video/x-flv"):
video_format = "flv"
elif mimetype.startswith("video/3gpp"):
video_format = "3gp"
elif mimetype.startswith("video/webm"):
video_format = "webm"
else:
video_format = "unknown"
if quality == "small":
video_quality = "240p"
video_priority = 5
elif quality == "medium":
video_quality = "360p"
video_priority = 4
elif quality == "large":
video_quality = "480p"
video_priority = 3
elif quality == "hd720":
video_quality = "720p"
video_priority = 2
elif quality == "hd1080":
video_quality = "1080p"
video_priority = 1
else:
video_quality = "unknown"
video_priority = 0
print "UNKNOWN: %s" % quality
stream_dict = {
'url' : video_url,
'quality' : video_quality,
'priority' : video_priority,
'format' : video_format,
'extra' : {
'itag': itag,
'mimetype': mimetype,
'fallback_host': fallback_host
}
}
stream_pool.append(stream_dict)
try:
video_title = unescape(re.search('<meta property="og:title" content="([^"]*)">', contents).group(1))
except:
self.state = "failed"
raise ResolverError("Could not find the video title.")
self.results = {
'title': video_title,
'videos': stream_pool
}
return { 'title': video_title, 'videos': stream_pool } self.state = "finished"
return self

41
resolv/shared.py
Unescape Escape View File

@ -1,4 +1,5 @@
from HTMLParser import HTMLParser from HTMLParser import HTMLParser
import cookielib, urllib2
import sys import sys
reload(sys) reload(sys)
@ -11,5 +12,45 @@ class ResolverError(Exception):
def __str__(self): def __str__(self):
return repr(self.val) return repr(self.val)
class Task():
captcha = None
cookiejar = None
useragent = "Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/536.11 (KHTML, like Gecko) Chrome/20.0.1132.47 Safari/536.11"
opener = None
results = None
state = "none"
url = ""
result_type = "none"
extra_headers = {}
def __init__(self, url):
self.cookiejar = cookielib.CookieJar()
self.opener = urllib2.build_opener(urllib2.HTTPCookieProcessor(self.cookiejar))
self.opener.addheaders = []
self.extra_headers['User-agent'] = self.useragent
for header, payload in self.extra_headers.iteritems():
self.opener.addheaders.append((header, payload))
self.url = url
def run(self):
self.state = "finished"
self.results = self.url
return self
def fetch_page(self, url):
return self.opener.open(url).read()
class Captcha():
image = ""
audio = ""
def __init__(image="", audio=""):
self.image = image
self.audio = audio
def unescape(s): def unescape(s):
return HTMLParser.unescape.__func__(HTMLParser, s) return HTMLParser.unescape.__func__(HTMLParser, s)

Write Preview
Loading…
Cancel
Save